Most previous work on differential privacy mainly focused on independent datasets, assuming that all records were sampled from a universe independently. However, in a real-world, many datasets contain strong coupling relations where some records are often correlated with each other. When such datasets are released, the definition of differential privacy will be violated as an adversary has a higher chance to obtain sensitive information. Hence, it is critical to find effective solutions to preserve rigorous differential privacy with correlated datasets. This chapter first formally defines the correlated differential privacy problem and outlines the research issues and challenges in providing privacy guarantees for correlated datasets. Then it presents an innovative solution to solve the correlated differential privacy problem and shows that the solution is robust and effective.
CITATION STYLE
Zhu, T., Li, G., Zhou, W., & Yu, P. S. (2017). Correlated differential privacy for non-IID datasets. In Advances in Information Security (Vol. 69, pp. 191–214). Springer New York LLC. https://doi.org/10.1007/978-3-319-62004-6_14
Mendeley helps you to discover research relevant for your work.